factual

Sora Models More Of The World Than Credited

Generative models like Sora understand more about a world model than people give them credit for—evidenced by behaviors like correctly maintaining an occluded object after a person walks in front of and away from it—even though obvious failures (like a cat sprouting an extra limb) make it easy to dismiss them as fake; the truth is some of it works and some doesn't, and it will improve with scale.

factualpending

Speaker

Sam Altman

Evidence Quote

“all of these models understand something more about the world model than most of us give them credit for. And because they’re also very clear things they just don’t understand or don’t get right, it’s easy to look at the weaknesses, see through the veil and say, “Ah, this is all fake.” But it’s not all fake.”

Source

Sam Altman #2— Lex Fridman Podcast
Created: 6/13/2026, 3:36:04 AM

Your notes

Loading notes...